diff --git a/.github/workflows/gpclean.lock.yml b/.github/workflows/gpclean.lock.yml index df15eaffc90..8a0eb2dad2b 100644 --- a/.github/workflows/gpclean.lock.yml +++ b/.github/workflows/gpclean.lock.yml @@ -1,4 +1,4 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"45165dcb223a372ca8e2c92b85c43faf672b6291014bf650f5b30b5b39b5f003","body_hash":"9a319e8c129ca199af41fd0816dc41f10994ae38a6a37c2c2cf0a82f9d9ebf54","agent_id":"codex","agent_model":"openai/gpt-5.4","engine_versions":{"codex":"0.150.1"}} +# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"26c3b1af9c55e22b4ca6c6fc1cfe61f3e57e17e86481311554aa58cce1e4983b","body_hash":"9a319e8c129ca199af41fd0816dc41f10994ae38a6a37c2c2cf0a82f9d9ebf54","agent_id":"codex","agent_model":"openai/gpt-5.3-codex","engine_versions":{"codex":"0.150.1"}} # gh-aw-manifest: {"version":1,"secrets":["CODEX_API_KEY","COPILOT_GITHUB_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GH_AW_OTEL_GRAFANA_AUTHORIZATION","GH_AW_OTEL_GRAFANA_ENDPOINT","GH_AW_OTEL_SENTRY_AUTHORIZATION","GH_AW_OTEL_SENTRY_ENDPOINT","GITHUB_TOKEN","OPENAI_API_KEY"],"actions":[{"repo":"actions/cache/restore","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/cache/save","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/download-artifact","sha":"3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c","version":"v8.0.1"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"820762786026740c76f36085b0efc47a31fe5020","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.28.10","digest":"sha256:c01e6d16d11ea4f2a46cc023a9f402224a3b3861b026818eec0dc586d7e6918e","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.28.10@sha256:c01e6d16d11ea4f2a46cc023a9f402224a3b3861b026818eec0dc586d7e6918e"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.10","digest":"sha256:c3a18aebb8251339117ea998296315de17bada366f8d03919b3348ea71112e64","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.10@sha256:c3a18aebb8251339117ea998296315de17bada366f8d03919b3348ea71112e64"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.28.10","digest":"sha256:c06076f7aca95df713e0748c44d80c0a3c2538fad67bfdd04296d45158e083e6","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.28.10@sha256:c06076f7aca95df713e0748c44d80c0a3c2538fad67bfdd04296d45158e083e6"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.13","digest":"sha256:ec4008521c610e1113ed557ecec0ff64a2c2111e4cfa817bab54d9b7da24c7cc","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.13@sha256:ec4008521c610e1113ed557ecec0ff64a2c2111e4cfa817bab54d9b7da24c7cc"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:bac2192f6374d6262116399b34fc5e143d576f82719e90a18261cae7480f4d4e","pinned_image":"ghcr.io/github/gh-aw-node@sha256:bac2192f6374d6262116399b34fc5e143d576f82719e90a18261cae7480f4d4e"},{"image":"ghcr.io/github/github-mcp-server:v1.11.0","digest":"sha256:fbec75de11c255213fa08d80fb166abe73d851fff631c51c0079872967720699","pinned_image":"ghcr.io/github/github-mcp-server:v1.11.0@sha256:fbec75de11c255213fa08d80fb166abe73d851fff631c51c0079872967720699"}],"mcp_servers":[{"name":"github","tools":["get_commit","get_file_contents","get_latest_release","get_me","get_pull_request","get_pull_request_comments","get_pull_request_diff","get_pull_request_files","get_pull_request_review_comments","get_pull_request_reviews","get_pull_request_status","get_release_by_tag","get_tag","issue_read","list_branches","list_commits","list_issue_types","list_issues","list_pull_requests","list_releases","list_starred_repositories","list_tags","pull_request_read","search_code","search_issues","search_pull_requests","search_repositories"]},{"name":"safeoutputs","tools":["create_issue","missing_data","missing_tool","noop"]}]} # This file was automatically generated by gh-aw. DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md # @@ -144,7 +144,7 @@ jobs: env: GH_AW_INFO_ENGINE_ID: "codex" GH_AW_INFO_ENGINE_NAME: "Codex" - GH_AW_INFO_MODEL: "openai/gpt-5.4" + GH_AW_INFO_MODEL: "openai/gpt-5.3-codex" GH_AW_INFO_VERSION: "0.150.1" GH_AW_INFO_AGENT_VERSION: "0.150.1" GH_AW_INFO_WORKFLOW_NAME: "GPL Dependency Cleaner (gpclean)" @@ -294,7 +294,7 @@ jobs: GH_AW_EXPERIMENT_SPEC: '{"tool_verbosity":{"variants":["full_bash","minimal_toolset"],"description":"Test whether restricting bash tools reduces cost without compromising GPL detection quality","hypothesis":"H0: no change in token consumption. H1: minimal toolset reduces tokens by 10-15% while maintaining issue quality (detection accuracy + alternative research depth)","metric":"effective_token_count","secondary_metrics":["run_duration_seconds","tools_invoked_count","issue_completeness_score"],"guardrail_metrics":[{"name":"gpl_detection_rate","threshold":"==100"},{"name":"issue_created_rate","threshold":"\u003e=90"}],"min_samples":30,"weight":[50,50],"start_date":"2026-05-24"}}' GH_AW_EXPERIMENT_STATE_FILE: /tmp/gh-aw/experiments/state.jsonl GH_AW_EXPERIMENT_STATE_DIR: /tmp/gh-aw/experiments - GH_AW_HARNESS_VERSION: 45165dcb223a372ca8e2c92b85c43faf672b6291014bf650f5b30b5b39b5f003:9a319e8c129ca199af41fd0816dc41f10994ae38a6a37c2c2cf0a82f9d9ebf54 + GH_AW_HARNESS_VERSION: 26c3b1af9c55e22b4ca6c6fc1cfe61f3e57e17e86481311554aa58cce1e4983b:9a319e8c129ca199af41fd0816dc41f10994ae38a6a37c2c2cf0a82f9d9ebf54 with: script: | const path = require('path'); @@ -1031,7 +1031,7 @@ jobs: GH_AW_LLM_PROVIDER: openai GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }} GH_AW_MCP_CONFIG: ${{ runner.temp }}/gh-aw/mcp-config/config.toml - GH_AW_MODEL_AGENT_CODEX: openai/gpt-5.4 + GH_AW_MODEL_AGENT_CODEX: openai/gpt-5.3-codex GH_AW_PHASE: agent GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} @@ -1743,7 +1743,7 @@ jobs: GH_AW_LLM_PROVIDER: openai GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }} GH_AW_MCP_CONFIG: ${{ runner.temp }}/gh-aw/mcp-config/config.toml - GH_AW_MODEL_DETECTION_CODEX: openai/gpt-5.4 + GH_AW_MODEL_DETECTION_CODEX: openai/gpt-5.3-codex GH_AW_PHASE: detection GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt GH_AW_VERSION: dev @@ -1917,7 +1917,7 @@ jobs: uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 env: GH_AW_EVALS_QUESTIONS: '[{"id":"issue-or-noop","question":"Did the agent either create a GPL dependency issue or call noop?"},{"id":"go-mod-analyzed","question":"Does the agent output confirm that go.mod was analyzed for GPL-licensed transitive dependencies?"},{"id":"decision-explained","question":"Does the agent output include an explanation of why a GPL issue was created or why noop was called?"},{"id":"tool_verbosity_goal_met","question":"Does the agent output show that the objective for experiment tool_verbosity was successfully completed?"}]' - GH_AW_EVALS_MODEL: "openai/gpt-5.4" + GH_AW_EVALS_MODEL: "openai/gpt-5.3-codex" GH_AW_EVALS_PHASE: setup with: script: | @@ -2077,7 +2077,7 @@ jobs: GH_AW_LLM_PROVIDER: openai GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }} GH_AW_MCP_CONFIG: ${{ runner.temp }}/gh-aw/mcp-config/config.toml - GH_AW_MODEL_EVALS_CODEX: openai/gpt-5.4 + GH_AW_MODEL_EVALS_CODEX: openai/gpt-5.3-codex GH_AW_PHASE: evals GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt GH_AW_VERSION: dev @@ -2109,7 +2109,7 @@ jobs: uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 env: GH_AW_EVALS_QUESTIONS: '[{"id":"issue-or-noop","question":"Did the agent either create a GPL dependency issue or call noop?"},{"id":"go-mod-analyzed","question":"Does the agent output confirm that go.mod was analyzed for GPL-licensed transitive dependencies?"},{"id":"decision-explained","question":"Does the agent output include an explanation of why a GPL issue was created or why noop was called?"},{"id":"tool_verbosity_goal_met","question":"Does the agent output show that the objective for experiment tool_verbosity was successfully completed?"}]' - GH_AW_EVALS_MODEL: "openai/gpt-5.4" + GH_AW_EVALS_MODEL: "openai/gpt-5.3-codex" GH_AW_EVALS_PHASE: parse GITHUB_RUN_ID: ${{ github.run_id }} with: @@ -2341,7 +2341,7 @@ jobs: GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }} GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }} GH_AW_ENGINE_ID: "codex" - GH_AW_ENGINE_MODEL: "openai/gpt-5.4" + GH_AW_ENGINE_MODEL: "openai/gpt-5.3-codex" GH_AW_PROJECT_UTC: "-08:00" GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} diff --git a/.github/workflows/gpclean.md b/.github/workflows/gpclean.md index bb45adab138..f8835c1a4d7 100644 --- a/.github/workflows/gpclean.md +++ b/.github/workflows/gpclean.md @@ -58,7 +58,7 @@ experiments: engine: id: codex model-provider: openai -model: openai/gpt-5.4 +model: openai/gpt-5.3-codex strict: false imports: